Thoughtspot, Inc.

Aditya Viswanathan

Ravi Tandon

Manikanta Balakavi

Rakesh Kothari

Amitabh Singhal

Amit Prakash

Ajeet Singh

Ashish Shubham

Pavan Ram Piratla

Maneesh Apte

Alonzo Canada

Manikanta Venkata Rahul Balakavi

A current set of context features for a database query that is associated with a string is identified. The database query includes a sequence of tokens of a database syntax, and the current set of context features includes words from the string and tokens from the database query. An inference record is selected from an inference store based on a comparison of the current set of context features to context features of inference records in the inference store. The database query is modified using a resolution of the inference record to obtain an inferred database query. The resolution includes one or more tokens of the database syntax. A search of a database is invoked using a query based on the inferred database query to obtain search results.

Natural language question answering systems

Performing, by a low-latency data access and analysis system, automatic grammar switching includes, in response to obtaining data indicating a request to switch from using a first defined grammar to using a second defined grammar, wherein the request includes data representing a first resolved-request generated for a first input string using the first defined grammar, generating, using the second defined grammar, a second resolved-request for the first input string, automatically generating a data-query in accordance with the second resolved-request, and outputting output data including results data obtained by executing the data-query.

Lossless switching between search grammars

Providing a search interface for a database includes receiving string data entered via a user interface. A sequence of tokens representative of the string data is determined. Determining the sequence of tokens includes applying natural language processing to the string data. A first database query is generated in accordance with the sequence of tokens. Respective text representations for tokens in the sequence of tokens are presented via the user interface. Feedback data related to the sequence of tokens is received via the user interface. A token of the sequence of tokens is modified based on the feedback data to obtain a modified sequence of tokens. A second database query is generated based on the modified sequence of tokens. Results data are obtained from the database responsive to execution of the second database query by the database. Data based on the results data are output for presentation in the user interface.

Lossless switching between search grammars is described herein. A method may include generating a first resolved-request using a relational search grammar in response to receiving a request for data, where the first resolved-request includes an ordered sequence of tokens, and in response to receiving a request for data indicating the first resolved-request and indicating a request to use a natural language search grammar, generating a second resolved-request in accordance with the natural language search grammar by identifying tokens and token binding data associated with the relational search grammar resolved-request as query refinements, generating the second resolved-request consistent with the first resolved-request by tokenizing the request for data associated with the natural language search grammar in accordance with the natural language search grammar using the query refinements, and outputting search results obtained using the request for data associated with the natural language search grammar using the natural language search grammar.

Systems and methods for natural language question answering are described. For example, methods may include determining a set of candidate database queries, including respective sequences of tokens of a database syntax, based on a string; determining a first score for a first candidate database query from the set of candidate database queries, wherein the first score is based on a match between one or more words of the string and a token of the respective sequence of tokens of the first candidate database query; determining a second score for the first candidate database query, wherein the second score is based on natural language syntax data determined for words of the string; selecting, based on the first score and the second score, the first candidate database query from the set of candidate database queries; and invoking a search of the database using the first candidate database query to obtain search results.

Growing community of inventors

Redwood City, CA, United States of America

Aditya Viswanathan